diff --git a/mindspore/lite/src/ops/expand_dims.cc b/mindspore/lite/src/ops/expand_dims.cc
index bbeef87bbc9..419eed0744f 100644
--- a/mindspore/lite/src/ops/expand_dims.cc
+++ b/mindspore/lite/src/ops/expand_dims.cc
@@ -51,8 +51,8 @@ int ExpandDims::UnPackAttr(const Primitive &prim, const std::vector<AnfNodePtr>
       return RET_ERROR;
     }
     // use axis instead of dim
-    if (inputs[1]->isa<ValueNode>()) {
-      auto axis_tensor = inputs[1]->cast<ValueNodePtr>();
+    if (inputs.at(1)->isa<ValueNode>()) {
+      auto axis_tensor = inputs.at(1)->cast<ValueNodePtr>();
       int axis = CastToInt(axis_tensor->value()).front();
       attr->dim = axis;
     } else {
diff --git a/mindspore/lite/src/ops/fill.cc b/mindspore/lite/src/ops/fill.cc
index 4c08e4b20a0..6fff1fe27e5 100644
--- a/mindspore/lite/src/ops/fill.cc
+++ b/mindspore/lite/src/ops/fill.cc
@@ -76,7 +76,7 @@ int Fill::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> output
 
   std::vector<int> output_shape;
   for (size_t i = 0; i < GetDims().size(); i++) {
-    output_shape.push_back(GetDims()[i]);
+    output_shape.push_back(GetDims().at(i));
   }
   output->set_shape(output_shape);
   return RET_OK;
diff --git a/mindspore/lite/src/ops/flatten.cc b/mindspore/lite/src/ops/flatten.cc
index 6555b266078..ed123fab2c3 100644
--- a/mindspore/lite/src/ops/flatten.cc
+++ b/mindspore/lite/src/ops/flatten.cc
@@ -45,10 +45,10 @@ int Flatten::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> out
 
   auto input_shape = input->shape();
   std::vector<int> output_shape(2);
-  output_shape[0] = input_shape[0];
-  output_shape[1] = 1;
+  output_shape.at(0) = input_shape.at(0);
+  output_shape.at(1) = 1;
   for (size_t i = 1; i < input_shape.size(); i++) {
-    output_shape[1] *= input_shape[i];
+    output_shape.at(1) *= input_shape.at(i);
   }
   output->set_shape(output_shape);
   return RET_OK;
diff --git a/mindspore/lite/src/ops/flatten_grad.cc b/mindspore/lite/src/ops/flatten_grad.cc
index 5796ce57027..8821470f866 100644
--- a/mindspore/lite/src/ops/flatten_grad.cc
+++ b/mindspore/lite/src/ops/flatten_grad.cc
@@ -44,10 +44,10 @@ int FlattenGrad::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *>
 
   auto input_shape = input->shape();
   std::vector<int> output_shape(2);
-  output_shape[0] = input_shape[0];
-  output_shape[1] = 1;
+  output_shape.at(0) = input_shape.at(0);
+  output_shape.at(1) = 1;
   for (size_t i = 1; i < input_shape.size(); i++) {
-    output_shape[1] *= input_shape[i];
+    output_shape.at(1) *= input_shape.at(i);
   }
   output->set_shape(output_shape);
   return RET_OK;
diff --git a/mindspore/lite/src/ops/full_connection.cc b/mindspore/lite/src/ops/full_connection.cc
index 24be3ce5d15..6d50ff56aff 100644
--- a/mindspore/lite/src/ops/full_connection.cc
+++ b/mindspore/lite/src/ops/full_connection.cc
@@ -65,7 +65,7 @@ int FullConnection::InferShape(std::vector<lite::Tensor *> inputs_, std::vector<
   MS_ASSERT(this->primitive_ != nullptr);
   auto input0 = inputs_.front();
   MS_ASSERT(input0 != nullptr);
-  auto input1 = inputs_[1];
+  auto input1 = inputs_.at(1);
   MS_ASSERT(input1 != nullptr);
   auto output = outputs_.front();
   MS_ASSERT(output != nullptr);
@@ -83,34 +83,34 @@ int FullConnection::InferShape(std::vector<lite::Tensor *> inputs_, std::vector<
   int new_k = 1;
   if (GetUseAxis()) {
     for (size_t i = GetAxis(); i < input0->shape().size(); ++i) {
-      new_k *= input0->shape()[i];
+      new_k *= input0->shape().at(i);
     }
-    if (new_k != input1->shape()[1]) {
+    if (new_k != input1->shape().at(1)) {
       MS_LOG(ERROR) << "Input1 size invalid";
       return RET_INPUT_TENSOR_ERROR;
     }
   } else {
-    new_k = input1->shape()[1];
+    new_k = input1->shape().at(1);
   }
   if (GetHasBias()) {
-    if (inputs_[2]->shape()[0] != input1->shape()[0]) {
+    if (inputs_.at(2)->shape().at(0) != input1->shape().at(0)) {
       MS_LOG(ERROR) << "bias size invalid";
       return RET_INPUT_TENSOR_ERROR;
     }
   }
-  std::vector<int> out_shape{inputs_[0]->shape()};
+  std::vector<int> out_shape{inputs_.at(0)->shape()};
   if (GetUseAxis()) {
     out_shape.resize(GetAxis() + 1);
-    out_shape[GetAxis()] = input1->shape()[0];
+    out_shape.at(GetAxis()) = input1->shape().at(0);
   } else {
     int total = 1;
     for (size_t i = 0; i < input0->shape().size(); ++i) {
-      total *= input0->shape()[i];
+      total *= input0->shape().at(i);
     }
     out_shape.resize(2);
     auto batch_size = total / new_k;
-    out_shape[0] = batch_size;
-    out_shape[1] = input1->shape()[0];
+    out_shape.at(0) = batch_size;
+    out_shape.at(1) = input1->shape().at(0);
   }
   output->set_shape(out_shape);
   output->set_data_type(input0->data_type());
diff --git a/mindspore/lite/src/ops/gather.cc b/mindspore/lite/src/ops/gather.cc
index 6e13952cec1..662062a3c53 100644
--- a/mindspore/lite/src/ops/gather.cc
+++ b/mindspore/lite/src/ops/gather.cc
@@ -57,8 +57,8 @@ int Gather::UnPackAttr(const Primitive &prim, const std::vector<AnfNodePtr> &inp
       gather_attr = nullptr;
       return RET_ERROR;
     }
-    if (inputs[2]->isa<ValueNode>()) {
-      ValueNodePtr axis_tensor = inputs[2]->cast<ValueNodePtr>();
+    if (inputs.at(2)->isa<ValueNode>()) {
+      ValueNodePtr axis_tensor = inputs.at(2)->cast<ValueNodePtr>();
       int axis = CastToInt(axis_tensor->value()).front();
       gather_attr->axis = axis;
     } else {
@@ -137,7 +137,7 @@ int Gather::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> outp
   std::vector<int> out_shape{in_shape};
   out_shape.erase(out_shape.begin() + axis);
   for (int i = indices_rank - 1; i >= 0; --i) {
-    out_shape.insert(out_shape.begin() + axis, indices_shape[i]);
+    out_shape.insert(out_shape.begin() + axis, indices_shape.at(i));
   }
   output->set_shape(out_shape);
   return RET_OK;
diff --git a/mindspore/lite/src/ops/gather_nd.cc b/mindspore/lite/src/ops/gather_nd.cc
index 1387b91cfc4..4f7523b0da3 100644
--- a/mindspore/lite/src/ops/gather_nd.cc
+++ b/mindspore/lite/src/ops/gather_nd.cc
@@ -72,17 +72,17 @@ int GatherNd::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> ou
   int in_rank = in_shape.size();
   auto indices_shape = indices->shape();
   int indices_rank = indices_shape.size();
-  if (indices_shape[indices_rank - 1] > in_rank) {
+  if (indices_shape.at(indices_rank - 1) > in_rank) {
     MS_LOG(ERROR) << "Input of indices data is error!";
     return RET_ERROR;
   }
   std::vector<int> out_shape;
   int i = 0;
   for (i = 0; i < indices_rank - 1; ++i) {
-    out_shape.emplace_back(indices_shape[i]);
+    out_shape.emplace_back(indices_shape.at(i));
   }
-  for (i = indices_shape[indices_rank - 1]; i < in_rank; ++i) {
-    out_shape.emplace_back(in_shape[i]);
+  for (i = indices_shape.at(indices_rank - 1); i < in_rank; ++i) {
+    out_shape.emplace_back(in_shape.at(i));
   }
   output->set_shape(out_shape);
   return RET_OK;
diff --git a/mindspore/lite/src/ops/layer_norm.cc b/mindspore/lite/src/ops/layer_norm.cc
index c26018764fa..acce63150d4 100644
--- a/mindspore/lite/src/ops/layer_norm.cc
+++ b/mindspore/lite/src/ops/layer_norm.cc
@@ -97,7 +97,7 @@ int LayerNorm::InferShape(std::vector<lite::Tensor *> inputs_, std::vector<lite:
   }
   size_t first_index = input_shape.size() - normalized_shape.size();
   for (size_t i = first_index; i < input_shape.size(); ++i) {
-    if (input_shape[i] != normalized_shape[i - first_index]) {
+    if (input_shape.at(i) != normalized_shape.at(i - first_index)) {
       MS_LOG(INFO) << "normalized_shape attr invalid";
       return RET_PARAM_INVALID;
     }
diff --git a/mindspore/lite/src/ops/lstm.cc b/mindspore/lite/src/ops/lstm.cc
index 25e7fc7311e..b66c9bc22b1 100644
--- a/mindspore/lite/src/ops/lstm.cc
+++ b/mindspore/lite/src/ops/lstm.cc
@@ -59,13 +59,13 @@ int Lstm::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> output
   }
   auto input = inputs_.front();
   MS_ASSERT(input != nullptr);
-  auto weight_i = inputs_[1];
-  MS_ASSERT(input != nullptr);
+  auto weight_i = inputs_.at(1);
+  MS_ASSERT(weight_i != nullptr);
   auto output = outputs_.front();
   MS_ASSERT(output != nullptr);
   for (int i = 0; i < kLstmOutputNum; i++) {
-    outputs_[i]->set_data_type(input->data_type());
-    outputs_[i]->set_format(input->format());
+    outputs_.at(i)->set_data_type(input->data_type());
+    outputs_.at(i)->set_format(input->format());
   }
   if (!infer_flag()) {
     return RET_OK;
diff --git a/mindspore/lite/src/ops/matmul.cc b/mindspore/lite/src/ops/matmul.cc
index f6d9eb3d6a8..a2d8fa00095 100644
--- a/mindspore/lite/src/ops/matmul.cc
+++ b/mindspore/lite/src/ops/matmul.cc
@@ -125,7 +125,7 @@ int MatMul::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> outp
     del_end = true;
   }
   for (size_t i = 0; i < (a_shape.size() - 2) && i < (b_shape.size() - 2); ++i) {
-    if (a_shape[a_shape.size() - 3 - i] != b_shape[b_shape.size() - 3 - i]) {
+    if (a_shape.at(a_shape.size() - 3 - i) != b_shape.at(b_shape.size() - 3 - i)) {
       MS_LOG(ERROR) << "Op MatMul's dimensions must be equal";
       return RET_INPUT_TENSOR_ERROR;
     }
diff --git a/mindspore/lite/src/ops/mean.cc b/mindspore/lite/src/ops/mean.cc
index e6be5f2fae2..843157b6ce7 100644
--- a/mindspore/lite/src/ops/mean.cc
+++ b/mindspore/lite/src/ops/mean.cc
@@ -103,7 +103,7 @@ int Mean::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> output
   for (size_t i = 0; i < in_shape.size(); i++) {
     bool reduce_axis = false;
     for (size_t idx = 0; idx < num_axes; ++idx) {
-      if (static_cast<size_t>(axes[idx]) == i) {
+      if (static_cast<size_t>(axes.at(idx)) == i) {
         reduce_axis = true;
         break;
       }
@@ -113,7 +113,7 @@ int Mean::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> output
         out_shape.push_back(1);
       }
     } else {
-      out_shape.push_back(in_shape[i]);
+      out_shape.push_back(in_shape.at(i));
     }
   }
   output->set_shape(out_shape);
diff --git a/mindspore/lite/src/ops/oneslike.cc b/mindspore/lite/src/ops/oneslike.cc
index 5ddd86ee010..f564195eb0c 100644
--- a/mindspore/lite/src/ops/oneslike.cc
+++ b/mindspore/lite/src/ops/oneslike.cc
@@ -72,8 +72,8 @@ PrimitiveC *OnesLikeCreator(const schema::Primitive *primitive) {
 Registry OnesLikeRegistry(schema::PrimitiveType_OnesLike, OnesLikeCreator);
 #endif
 int OnesLike::InferShape(std::vector<Tensor *> inputs_, std::vector<Tensor *> outputs_) {
-  Tensor *x = inputs_[0];
-  Tensor *out = outputs_[0];
+  Tensor *x = inputs_.at(0);
+  Tensor *out = outputs_.at(0);
   std::vector<int> x_shape = x->shape();
   std::vector<int> output_shape(x_shape.size());
   output_shape.assign(x_shape.begin(), x_shape.end());
diff --git a/mindspore/lite/src/ops/pad.cc b/mindspore/lite/src/ops/pad.cc
index 4d96c9195a8..5a3c7145dca 100644
--- a/mindspore/lite/src/ops/pad.cc
+++ b/mindspore/lite/src/ops/pad.cc
@@ -110,7 +110,7 @@ int Pad::InferShape(std::vector<Tensor *> inputs, std::vector<Tensor *> outputs)
   MS_ASSERT(input->shape().size() <= 4);
   for (size_t i = 0; i < input_shape.size(); i++) {
     auto paddings_index = i;
-    auto shape = input_shape[i] + paddings[2 * paddings_index] + paddings[2 * paddings_index + 1];
+    auto shape = input_shape.at(i) + paddings.at(2 * paddings_index) + paddings.at(2 * paddings_index + 1);
     output_shape.push_back(shape);
   }
 
diff --git a/mindspore/lite/src/ops/pooling.cc b/mindspore/lite/src/ops/pooling.cc
index 329665e807c..57b4de165b1 100644
--- a/mindspore/lite/src/ops/pooling.cc
+++ b/mindspore/lite/src/ops/pooling.cc
@@ -111,12 +111,12 @@ int Pooling::UnPackAttr(const Primitive &prim, const std::vector<AnfNodePtr> &in
     }
 
     auto kernel_size = CastToInt(prim.GetAttr("ksize"));
-    attr->windowH = kernel_size[2];
-    attr->windowW = kernel_size[3];
+    attr->windowH = kernel_size.at(2);
+    attr->windowW = kernel_size.at(3);
 
     auto stride = CastToInt(prim.GetAttr("strides"));
-    attr->strideH = stride[2];
-    attr->strideW = stride[3];
+    attr->strideH = stride.at(2);
+    attr->strideW = stride.at(3);
     this->primitive_->value.value = attr;
     if (this->primitive_->value.value == nullptr) {
       MS_LOG(ERROR) << "primitive value is nullptr";
diff --git a/mindspore/lite/src/ops/pooling_grad.cc b/mindspore/lite/src/ops/pooling_grad.cc
index 7afa0e41023..ffe8d8dcec1 100644
--- a/mindspore/lite/src/ops/pooling_grad.cc
+++ b/mindspore/lite/src/ops/pooling_grad.cc
@@ -100,12 +100,12 @@ int PoolingGrad::UnPackAttr(const Primitive &prim, const std::vector<AnfNodePtr>
     }
 
     auto kernel_size = CastToInt(prim.GetAttr("ksize"));
-    attr->windowH = kernel_size[2];
-    attr->windowW = kernel_size[3];
+    attr->windowH = kernel_size.at(2);
+    attr->windowW = kernel_size.at(3);
 
     auto stride = CastToInt(prim.GetAttr("strides"));
-    attr->strideH = stride[2];
-    attr->strideW = stride[3];
+    attr->strideH = stride.at(2);
+    attr->strideW = stride.at(3);
     this->primitive_->value.value = attr;
     if (this->primitive_->value.value == nullptr) {
       MS_LOG(ERROR) << "primitive value is nullptr";
diff --git a/mindspore/lite/src/ops/power.cc b/mindspore/lite/src/ops/power.cc
index f2c288ecfa0..17d85424f44 100644
--- a/mindspore/lite/src/ops/power.cc
+++ b/mindspore/lite/src/ops/power.cc
@@ -103,14 +103,14 @@ Registry PowerRegistry(schema::PrimitiveType_Power, PowerCreator);
 
 int Power::InferShape(std::vector<Tensor *> inputs, std::vector<Tensor *> outputs) {
   MS_ASSERT(this->primitive_ != nullptr);
-  auto x_tensor = inputs[0];
+  auto x_tensor = inputs.at(0);
   MS_ASSERT(x_tensor != nullptr);
   Tensor *exp_tensor = nullptr;
   if (inputs.size() == 2) {
-    exp_tensor = inputs[1];
+    exp_tensor = inputs.at(1);
     MS_ASSERT(exp_tensor != nullptr);
   }
-  auto output_tensor = outputs[0];
+  auto output_tensor = outputs.at(0);
   MS_ASSERT(output_tensor != nullptr);
   output_tensor->set_data_type(x_tensor->data_type());
   output_tensor->set_format(x_tensor->format());
@@ -119,7 +119,7 @@ int Power::InferShape(std::vector<Tensor *> inputs, std::vector<Tensor *> output
   }
   if (exp_tensor != nullptr) {
     if ((exp_tensor->shape().size() > 1 && exp_tensor->shape() != x_tensor->shape()) ||
-        (exp_tensor->shape().size() == 1 && exp_tensor->shape()[0] != 1) ||
+        (exp_tensor->shape().size() == 1 && exp_tensor->shape().at(0) != 1) ||
         exp_tensor->data_type() != x_tensor->data_type()) {
       MS_LOG(ERROR) << "Power inputs shape or type is not equal!";
       return RET_INPUT_TENSOR_ERROR;
diff --git a/mindspore/lite/src/ops/primitive_c.cc b/mindspore/lite/src/ops/primitive_c.cc
index 17a31645fb3..ef93c8036af 100644
--- a/mindspore/lite/src/ops/primitive_c.cc
+++ b/mindspore/lite/src/ops/primitive_c.cc
@@ -331,7 +331,7 @@ void PrimitiveC::GetAttrDataFromInput(const AnfNodePtr &inputNode, std::vector<i
       auto tuple = val->cast<ValueTuplePtr>();
       MS_ASSERT(tuple != nullptr);
       for (size_t i = 0; i < tuple->size(); i++) {
-        auto elem = tuple->value()[i];
+        auto elem = tuple->value().at(i);
         MS_ASSERT(elem != nullptr);
         data->emplace_back(CastToInt(elem).front());
       }
@@ -349,7 +349,7 @@ void PrimitiveC::set_input_quant_params(const std::vector<std::vector<schema::Qu
 
 void PrimitiveC::set_input_quant_param(const size_t &index, const std::vector<schema::QuantParamT> &input_quant_param) {
   MS_ASSERT(index < this->input_quant_param_.size());
-  this->input_quant_param_[index] = input_quant_param;
+  this->input_quant_param_.at(index) = input_quant_param;
 }
 
 void PrimitiveC::set_output_quant_params(const std::vector<std::vector<schema::QuantParamT>> &output_quant_param) {
@@ -359,7 +359,7 @@ void PrimitiveC::set_output_quant_params(const std::vector<std::vector<schema::Q
 void PrimitiveC::set_output_quant_param(const size_t &index,
                                         const std::vector<schema::QuantParamT> &output_quant_param) {
   MS_ASSERT(index < this->output_quant_param_.size());
-  this->output_quant_param_[index] = output_quant_param;
+  this->output_quant_param_.at(index) = output_quant_param;
 }
 
 bool PrimitiveC::IsInputQuantParamsInited() {
diff --git a/mindspore/lite/src/runtime/kernel/arm/base/prior_box.cc b/mindspore/lite/src/runtime/kernel/arm/base/prior_box.cc
index 6b5db11559a..b190e822b5a 100644
--- a/mindspore/lite/src/runtime/kernel/arm/base/prior_box.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/base/prior_box.cc
@@ -58,11 +58,11 @@ int PriorBoxCPUKernel::Init() {
 int PriorBoxCPUKernel::ReSize() { return GeneratePriorBox(); }
 
 int PriorBoxCPUKernel::GeneratePriorBox() {
-  const int fmap_w = in_tensors_[0]->Width();
-  const int fmap_h = in_tensors_[0]->Height();
+  const int fmap_w = in_tensors_.at(0)->Width();
+  const int fmap_h = in_tensors_.at(0)->Height();
 
-  const int image_w = prior_box_param_->image_size_w > 0 ? prior_box_param_->image_size_w : in_tensors_[1]->Width();
-  const int image_h = prior_box_param_->image_size_h > 0 ? prior_box_param_->image_size_h : in_tensors_[1]->Height();
+  const int image_w = prior_box_param_->image_size_w > 0 ? prior_box_param_->image_size_w : in_tensors_.at(1)->Width();
+  const int image_h = prior_box_param_->image_size_h > 0 ? prior_box_param_->image_size_h : in_tensors_.at(1)->Height();
 
   const float step_w =
     prior_box_param_->step_w > 0.0f ? prior_box_param_->step_w : static_cast<float>(image_w) / fmap_w;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp16/fullconnection_fp16.cc b/mindspore/lite/src/runtime/kernel/arm/fp16/fullconnection_fp16.cc
index 18ed44385b0..0397f1cd814 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp16/fullconnection_fp16.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp16/fullconnection_fp16.cc
@@ -54,10 +54,10 @@ void FullconnectionFP16CPUKernel::FreeTmpBuffer() {
 int FullconnectionFP16CPUKernel::ReSize() {
   FreeTmpBuffer();
   int row = 1;
-  for (size_t i = 0; i < out_tensors_[0]->shape().size() - 1; ++i) row *= (out_tensors_[0]->shape())[i];
+  for (size_t i = 0; i < out_tensors_.at(0)->shape().size() - 1; ++i) row *= (out_tensors_.at(0)->shape())[i];
   fc_param_->row_ = row;
-  fc_param_->col_ = out_tensors_[0]->shape().back();
-  fc_param_->deep_ = (in_tensors_[1]->shape())[1];
+  fc_param_->col_ = out_tensors_.at(0)->shape().back();
+  fc_param_->deep_ = (in_tensors_.at(1)->shape()).at(1);
   fc_param_->row_16_ = UP_ROUND(fc_param_->row_, C16NUM);
   fc_param_->col_8_ = UP_ROUND(fc_param_->col_, C8NUM);
   thread_count_ = MSMIN(thread_count_, UP_DIV(fc_param_->col_, C8NUM));
@@ -89,21 +89,21 @@ int FullconnectionFP16CPUKernel::ReSize() {
   }
   memset(b_pack_ptr_, 0, b_pack_col * fc_param_->deep_ * sizeof(float16_t));
 
-  fc_param_->b_const_ = (in_tensors_[1]->data_c() != nullptr);
+  fc_param_->b_const_ = (in_tensors_.at(1)->data_c() != nullptr);
   if (fc_param_->b_const_) {
-    if (in_tensors_[1]->data_type() == kNumberTypeFloat32) {
+    if (in_tensors_.at(1)->data_type() == kNumberTypeFloat32) {
       if (is_vector_input_) {
-        Float32ToFloat16(reinterpret_cast<float *>(in_tensors_[1]->data_c()), b_pack_ptr_,
+        Float32ToFloat16(reinterpret_cast<float *>(in_tensors_.at(1)->data_c()), b_pack_ptr_,
                          fc_param_->col_ * fc_param_->deep_);
       } else {
-        InitMatrixB(reinterpret_cast<float *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+        InitMatrixB(reinterpret_cast<float *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
       }
     } else {
       if (is_vector_input_) {
-        memcpy(b_pack_ptr_, reinterpret_cast<float16_t *>(in_tensors_[1]->data_c()),
+        memcpy(b_pack_ptr_, reinterpret_cast<float16_t *>(in_tensors_.at(1)->data_c()),
                fc_param_->col_ * fc_param_->deep_ * sizeof(float16_t));
       } else {
-        InitMatrixB(reinterpret_cast<float16_t *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+        InitMatrixB(reinterpret_cast<float16_t *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
       }
     }
     b_ptr_ = b_pack_ptr_;
@@ -116,10 +116,10 @@ int FullconnectionFP16CPUKernel::ReSize() {
       return RET_MEMORY_FAILED;
     }
     memset(bias_ptr_, 0, b_pack_col * sizeof(float16_t));
-    Float32ToFloat16(reinterpret_cast<float *>(in_tensors_[2]->data_c()), bias_ptr_, fc_param_->col_);
+    Float32ToFloat16(reinterpret_cast<float *>(in_tensors_.at(2)->data_c()), bias_ptr_, fc_param_->col_);
   }
 
-  if (out_tensors_[0]->data_type() == kNumberTypeFloat32) {
+  if (out_tensors_.at(0)->data_type() == kNumberTypeFloat32) {
     output_fp16_ =
       reinterpret_cast<float16_t *>(ctx_->allocator->Malloc(fc_param_->row_ * fc_param_->col_ * sizeof(float16_t)));
     if (output_fp16_ == nullptr) {
@@ -183,43 +183,43 @@ int FcFP16Run(void *cdata, int task_id) {
 }
 
 int FullconnectionFP16CPUKernel::Run() {
-  auto out_tensor = out_tensors_[0];
+  auto out_tensor = out_tensors_.at(0);
   if (out_tensor->data_type() == kNumberTypeFloat32) {
     output_ptr_ = output_fp16_;
   } else {
     output_ptr_ = reinterpret_cast<float16_t *>(out_tensor->data_c());
   }
 
-  if (in_tensors_[0]->data_type() == kNumberTypeFloat32) {
+  if (in_tensors_.at(0)->data_type() == kNumberTypeFloat32) {
     if (is_vector_input_) {
-      Float32ToFloat16(reinterpret_cast<float *>(in_tensors_[0]->data_c()), a_pack_ptr_, fc_param_->deep_);
+      Float32ToFloat16(reinterpret_cast<float *>(in_tensors_.at(0)->data_c()), a_pack_ptr_, fc_param_->deep_);
     } else {
-      InitMatrixA(reinterpret_cast<float *>(in_tensors_[0]->data_c()), a_pack_ptr_);
+      InitMatrixA(reinterpret_cast<float *>(in_tensors_.at(0)->data_c()), a_pack_ptr_);
     }
     a_ptr_ = a_pack_ptr_;
   } else {
     if (is_vector_input_) {
-      a_ptr_ = reinterpret_cast<float16_t *>(in_tensors_[0]->data_c());
+      a_ptr_ = reinterpret_cast<float16_t *>(in_tensors_.at(0)->data_c());
     } else {
-      InitMatrixA(reinterpret_cast<float16_t *>(in_tensors_[0]->data_c()), a_pack_ptr_);
+      InitMatrixA(reinterpret_cast<float16_t *>(in_tensors_.at(0)->data_c()), a_pack_ptr_);
       a_ptr_ = a_pack_ptr_;
     }
   }
 
   if (!fc_param_->b_const_) {
-    if (in_tensors_[1]->data_type() == kNumberTypeFloat32) {
+    if (in_tensors_.at(1)->data_type() == kNumberTypeFloat32) {
       if (is_vector_input_) {
-        Float32ToFloat16(reinterpret_cast<float *>(in_tensors_[1]->data_c()), b_pack_ptr_,
+        Float32ToFloat16(reinterpret_cast<float *>(in_tensors_.at(1)->data_c()), b_pack_ptr_,
                          fc_param_->col_ * fc_param_->deep_);
       } else {
-        InitMatrixB(reinterpret_cast<float *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+        InitMatrixB(reinterpret_cast<float *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
       }
       b_ptr_ = b_pack_ptr_;
     } else {
       if (is_vector_input_) {
-        b_ptr_ = reinterpret_cast<float16_t *>(in_tensors_[1]->data_c());
+        b_ptr_ = reinterpret_cast<float16_t *>(in_tensors_.at(1)->data_c());
       } else {
-        InitMatrixB(reinterpret_cast<float16_t *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+        InitMatrixB(reinterpret_cast<float16_t *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
         b_ptr_ = b_pack_ptr_;
       }
     }
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp16/group_convolution_fp16.cc b/mindspore/lite/src/runtime/kernel/arm/fp16/group_convolution_fp16.cc
index a1ec3a827fc..90e696650dd 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp16/group_convolution_fp16.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp16/group_convolution_fp16.cc
@@ -28,7 +28,7 @@ using mindspore::schema::PrimitiveType_Conv2D;
 namespace mindspore::kernel {
 int GroupConvolutionFP16CPUKernel::Init() {
   for (int i = 0; i < group_num_; ++i) {
-    auto ret = group_convs_[i]->Init();
+    auto ret = group_convs_.at(i)->Init();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "Sub kernel init failed.";
       return ret;
@@ -40,7 +40,7 @@ int GroupConvolutionFP16CPUKernel::Init() {
 
 int GroupConvolutionFP16CPUKernel::ReSize() {
   for (int i = 0; i < group_num_; ++i) {
-    auto ret = group_convs_[i]->ReSize();
+    auto ret = group_convs_.at(i)->ReSize();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "Sub kernel resize failed.";
       return RET_ERROR;
@@ -94,7 +94,7 @@ int GroupConvolutionFP16CPUKernel::PreProcess() {
       int in_w = conv_param_->input_w_;
       int in_c = conv_param_->input_channel_;
       in_shape = {in_batch, in_h, in_w, in_c};
-      auto sub_kernel_in_tensor = group_convs_[i]->in_tensors().front();
+      auto sub_kernel_in_tensor = group_convs_.at(i)->in_tensors().front();
       sub_kernel_in_tensor->set_shape(in_shape);
       ret = sub_kernel_in_tensor->MallocData();
       if (ret != RET_OK) {
@@ -141,9 +141,9 @@ int GroupConvolutionFP16CPUKernel::SeparateInput(int group_id) {
   int in_plane = in_h * in_w;
   int sub_in_channel = conv_param_->input_channel_;
   int ori_in_channel = sub_in_channel * group_num_;
-  auto sub_in_data = group_convs_[group_id]->in_tensors().front()->data_c();
+  auto sub_in_data = group_convs_.at(group_id)->in_tensors().front()->data_c();
   auto in_data_type = in_tensors_.front()->data_type();
-  auto sub_in_data_type = group_convs_[group_id]->in_tensors().front()->data_type();
+  auto sub_in_data_type = group_convs_.at(group_id)->in_tensors().front()->data_type();
   if (in_data_type != sub_in_data_type) {
     MS_LOG(ERROR) << "data type of sub conv kernel input should be the same as origin input's.";
     return RET_ERROR;
@@ -183,7 +183,7 @@ void GroupConvolutionFP16CPUKernel::PostConcat(int group_id) {
   int out_plane = out_h * out_w;
   int sub_out_channel = conv_param_->output_channel_;
   int ori_out_channel = sub_out_channel * group_num_;
-  auto sub_out_data = reinterpret_cast<float16_t *>(group_convs_[group_id]->out_tensors().front()->data_c());
+  auto sub_out_data = reinterpret_cast<float16_t *>(group_convs_.at(group_id)->out_tensors().front()->data_c());
   MS_ASSERT(sub_out_data);
   float16_t *src_ptr = sub_out_data;
   float16_t *dst_ptr = ori_out_data_ + group_id * sub_out_channel;
@@ -206,7 +206,7 @@ int GroupConvolutionFP16CPUKernel::Run() {
       return ret;
     }
     // sun kernels run
-    ret = group_convs_[i]->Run();
+    ret = group_convs_.at(i)->Run();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "sub kernel " << i << " execute failed.";
       return ret;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp16/matmul_fp16.cc b/mindspore/lite/src/runtime/kernel/arm/fp16/matmul_fp16.cc
index da44a9c5b75..d9c96b4e77b 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp16/matmul_fp16.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp16/matmul_fp16.cc
@@ -262,7 +262,7 @@ int MatmulFP16Run(void *cdata, int task_id) {
 }
 
 int MatmulFP16CPUKernel::Run() {
-  auto out_tensor = out_tensors_[0];
+  auto out_tensor = out_tensors_.at(0);
   auto ret = MallocFp16Output();
   if (ret != RET_OK) {
     MS_LOG(ERROR) << "Matmul MallocFp16Output failed";
@@ -280,10 +280,10 @@ int MatmulFP16CPUKernel::Run() {
       MS_LOG(ERROR) << "Matmul fp16 malloc matrix A buffer failed";
       return RET_ERROR;
     }
-    if (in_tensors_[0]->data_type() == kNumberTypeFloat32) {
-      InitMatrixA(reinterpret_cast<float *>(in_tensors_[0]->data_c()), a_pack_ptr_);
+    if (in_tensors_.at(0)->data_type() == kNumberTypeFloat32) {
+      InitMatrixA(reinterpret_cast<float *>(in_tensors_.at(0)->data_c()), a_pack_ptr_);
     } else {
-      InitMatrixA(reinterpret_cast<float16_t *>(in_tensors_[0]->data_c()), a_pack_ptr_);
+      InitMatrixA(reinterpret_cast<float16_t *>(in_tensors_.at(0)->data_c()), a_pack_ptr_);
     }
   }
   if (!params_->b_const_) {
@@ -292,10 +292,10 @@ int MatmulFP16CPUKernel::Run() {
       MS_LOG(ERROR) << "Matmul fp16 malloc matrix B buffer failed";
       return RET_ERROR;
     }
-    if (in_tensors_[1]->data_type() == kNumberTypeFloat32) {
-      InitMatrixB(reinterpret_cast<float *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+    if (in_tensors_.at(1)->data_type() == kNumberTypeFloat32) {
+      InitMatrixB(reinterpret_cast<float *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
     } else {
-      InitMatrixB(reinterpret_cast<float16_t *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+      InitMatrixB(reinterpret_cast<float16_t *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
     }
   }
   for (int i = 0; i < params_->batch; ++i) {
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp16/quant_dtype_cast_fp16.cc b/mindspore/lite/src/runtime/kernel/arm/fp16/quant_dtype_cast_fp16.cc
index 0d16a96d9a8..8373ddee83e 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp16/quant_dtype_cast_fp16.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp16/quant_dtype_cast_fp16.cc
@@ -115,14 +115,14 @@ int QuantDTypeCastFP16Run(void *cdata, int task_id) {
 }
 
 int QuantDTypeCastFp16CPUKernel::Run() {
-  if (in_tensors_[0]->data_type() == TypeId::kNumberTypeInt8 &&
-      out_tensors_[0]->data_type() == TypeId::kNumberTypeFloat16) {
-    int8_ptr_ = reinterpret_cast<int8_t *>(in_tensors_[0]->data_c());
-    float16_ptr_ = reinterpret_cast<float16_t *>(out_tensors_[0]->data_c());
-  } else if (in_tensors_[0]->data_type() == TypeId::kNumberTypeFloat16 &&
-             out_tensors_[0]->data_type() == TypeId::kNumberTypeInt8) {
-    float16_ptr_ = reinterpret_cast<float16_t *>(in_tensors_[0]->data_c());
-    int8_ptr_ = reinterpret_cast<int8_t *>(out_tensors_[0]->data_c());
+  if (in_tensors_.at(0)->data_type() == TypeId::kNumberTypeInt8 &&
+      out_tensors_.at(0)->data_type() == TypeId::kNumberTypeFloat16) {
+    int8_ptr_ = reinterpret_cast<int8_t *>(in_tensors_.at(0)->data_c());
+    float16_ptr_ = reinterpret_cast<float16_t *>(out_tensors_.at(0)->data_c());
+  } else if (in_tensors_.at(0)->data_type() == TypeId::kNumberTypeFloat16 &&
+             out_tensors_.at(0)->data_type() == TypeId::kNumberTypeInt8) {
+    float16_ptr_ = reinterpret_cast<float16_t *>(in_tensors_.at(0)->data_c());
+    int8_ptr_ = reinterpret_cast<int8_t *>(out_tensors_.at(0)->data_c());
   } else {
     MS_LOG(ERROR) << "QuantDTypeCastFp16 not support input or output type";
     return RET_ERROR;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/expandDims_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/expandDims_fp32.cc
index 7d50357d929..3b8cac575c2 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/expandDims_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/expandDims_fp32.cc
@@ -48,14 +48,14 @@ int ExpandDimsCPUKernel::DoExpandDims(int task_id) {
     return RET_OK;
   }
   int offset = task_id * thread_sz_stride_;
-  if (this->in_tensors_[0]->data_type() == kNumberTypeFloat32) {
+  if (this->in_tensors_.at(0)->data_type() == kNumberTypeFloat32) {
     int ret = ExpandDims(reinterpret_cast<float *>(in_ptr_) + offset, reinterpret_cast<float *>(out_ptr_) + offset,
                          size * sizeof(float));
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "ExpandDimsRun error task_id[" << task_id << "] error_code[" << ret << "]";
       return ret;
     }
-  } else if (this->in_tensors_[0]->data_type() == kNumberTypeInt8) {
+  } else if (this->in_tensors_.at(0)->data_type() == kNumberTypeInt8) {
     int ret = ExpandDims(reinterpret_cast<int8_t *>(in_ptr_) + offset, reinterpret_cast<int8_t *>(out_ptr_) + offset,
                          size * sizeof(int8_t));
     if (ret != RET_OK) {
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/flatten_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/flatten_fp32.cc
index 7ed6d69c74e..5ac9e164bca 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/flatten_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/flatten_fp32.cc
@@ -35,17 +35,17 @@ int FlattenCPUKernel::Init() {
 }
 
 int FlattenCPUKernel::ReSize() {
-  auto output_shape = out_tensors_[0]->shape();
+  auto output_shape = out_tensors_.at(0)->shape();
   flatten_param_->size = sizeof(float);
   for (size_t i = 0; i < output_shape.size(); i++) {
-    flatten_param_->size *= output_shape[i];
+    flatten_param_->size *= output_shape.at(i);
   }
   return RET_OK;
 }
 
 int FlattenCPUKernel::Run() {
-  auto input = reinterpret_cast<float *>(in_tensors_[0]->MutableData());
-  auto output = reinterpret_cast<float *>(out_tensors_[0]->MutableData());
+  auto input = reinterpret_cast<float *>(in_tensors_.at(0)->MutableData());
+  auto output = reinterpret_cast<float *>(out_tensors_.at(0)->MutableData());
   Flatten(input, output, flatten_param_);
   return RET_OK;
 }
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/fullconnection_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/fullconnection_fp32.cc
index cdb3e950779..04d02b1f1f9 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/fullconnection_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/fullconnection_fp32.cc
@@ -44,12 +44,12 @@ void FullconnectionCPUKernel::FreeBuf() {
 int FullconnectionCPUKernel::ReSize() {
   FreeBuf();
   int row = 1;
-  for (size_t i = 0; i < out_tensors_[0]->shape().size() - 1; ++i) {
-    row *= (out_tensors_[0]->shape())[i];
+  for (size_t i = 0; i < out_tensors_.at(0)->shape().size() - 1; ++i) {
+    row *= (out_tensors_.at(0)->shape())[i];
   }
   fc_param_->row_ = row;
-  fc_param_->col_ = out_tensors_[0]->shape().back();
-  fc_param_->deep_ = (in_tensors_[1]->shape())[1];
+  fc_param_->col_ = out_tensors_.at(0)->shape().back();
+  fc_param_->deep_ = (in_tensors_.at(1)->shape()).at(1);
 
   fc_param_->row_12_ = UP_ROUND(fc_param_->row_, C12NUM);
   fc_param_->col_8_ = UP_ROUND(fc_param_->col_, C8NUM);
@@ -98,14 +98,14 @@ int FullconnectionCPUKernel::ReSize() {
   }
   memset(b_pack_ptr_, 0, col_tmp * fc_param_->deep_ * sizeof(float));
 
-  fc_param_->a_const_ = (in_tensors_[0]->data_c() != nullptr);
-  fc_param_->b_const_ = (in_tensors_[1]->data_c() != nullptr);
+  fc_param_->a_const_ = (in_tensors_.at(0)->data_c() != nullptr);
+  fc_param_->b_const_ = (in_tensors_.at(1)->data_c() != nullptr);
   if (fc_param_->a_const_) {
-    InitMatrixA(reinterpret_cast<float *>(in_tensors_[0]->MutableData()), a_pack_ptr_);
+    InitMatrixA(reinterpret_cast<float *>(in_tensors_.at(0)->MutableData()), a_pack_ptr_);
     a_ptr_ = a_pack_ptr_;
   }
   if (fc_param_->b_const_) {
-    InitMatrixB(reinterpret_cast<float *>(in_tensors_[1]->MutableData()), b_pack_ptr_);
+    InitMatrixB(reinterpret_cast<float *>(in_tensors_.at(1)->MutableData()), b_pack_ptr_);
     b_ptr_ = b_pack_ptr_;
   }
   return RET_OK;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/fused_batchnorm_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/fused_batchnorm_fp32.cc
index 156cc41adec..9dcd0b792ae 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/fused_batchnorm_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/fused_batchnorm_fp32.cc
@@ -42,10 +42,10 @@ void FusedBatchnormCPUKernel::FreeScaleAndOffset() {
 }
 
 int FusedBatchnormCPUKernel::InitConstTensor() {
-  auto scale = in_tensors_[1];
-  auto offset = in_tensors_[2];
-  auto mean = in_tensors_[3];
-  auto variance = in_tensors_[4];
+  auto scale = in_tensors_.at(1);
+  auto offset = in_tensors_.at(2);
+  auto mean = in_tensors_.at(3);
+  auto variance = in_tensors_.at(4);
 
   scale_ = malloc(scale->Size());
   offset_ = malloc(offset->Size());
@@ -82,10 +82,10 @@ int FusedBatchnormCPUKernel::Run() {
     FusedBatchNormFp32MeanVar(in, current_mean, current_var, param, static_cast<float *>(save_mean),
                               static_cast<float *>(save_variance));
 
-    memcpy(out_tensors_[1]->MutableData(), scale, out_tensors_[1]->Size());
-    memcpy(out_tensors_[2]->MutableData(), offset, out_tensors_[2]->Size());
-    memcpy(out_tensors_[3]->MutableData(), current_mean, out_tensors_[3]->Size());
-    memcpy(out_tensors_[4]->MutableData(), current_var, out_tensors_[4]->Size());
+    memcpy(out_tensors_.at(1)->MutableData(), scale, out_tensors_.at(1)->Size());
+    memcpy(out_tensors_.at(2)->MutableData(), offset, out_tensors_.at(2)->Size());
+    memcpy(out_tensors_.at(3)->MutableData(), current_mean, out_tensors_.at(3)->Size());
+    memcpy(out_tensors_.at(4)->MutableData(), current_var, out_tensors_.at(4)->Size());
 
     // Copy to local variables
     memcpy(scale_, scale, in_tensors_[1]->Size());
@@ -108,16 +108,16 @@ int FusedBatchnormCPUKernel::Run() {
 int FusedBatchnormCPUKernel::Eval() {
   LiteKernel::Eval();
   if (trained_) {
-    float *save_mean = static_cast<float *>(in_tensors_[3]->MutableData());
-    float *save_var = static_cast<float *>(in_tensors_[4]->MutableData());
-    float *scale = static_cast<float *>(in_tensors_[1]->MutableData());
-    float *bias = static_cast<float *>(in_tensors_[2]->MutableData());
+    float *save_mean = static_cast<float *>(in_tensors_.at(3)->MutableData());
+    float *save_var = static_cast<float *>(in_tensors_.at(4)->MutableData());
+    float *scale = static_cast<float *>(in_tensors_.at(1)->MutableData());
+    float *bias = static_cast<float *>(in_tensors_.at(2)->MutableData());
 
     // Copy to local variables
-    memcpy(scale_, scale, in_tensors_[1]->Size());
-    memcpy(offset_, bias, in_tensors_[2]->Size());
-    memcpy(mean_, save_mean, in_tensors_[3]->Size());
-    memcpy(variance_, save_var, in_tensors_[4]->Size());
+    memcpy(scale_, scale, in_tensors_.at(1)->Size());
+    memcpy(offset_, bias, in_tensors_.at(2)->Size());
+    memcpy(mean_, save_mean, in_tensors_.at(3)->Size());
+    memcpy(variance_, save_var, in_tensors_.at(4)->Size());
   }
   return RET_OK;
 }
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/gatherNd_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/gatherNd_fp32.cc
index 3c857bd2185..8834aa7dc4e 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/gatherNd_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/gatherNd_fp32.cc
@@ -84,7 +84,7 @@ int GatherNdCPUKernel::ReSize() {
   int idx_stride = idx_lastshape;
   for (int j = 0; j < count_; ++j) {
     for (int k = 0; k < idx_lastshape; ++k) {
-      in_offset_[j] += indices_ptr[j * idx_stride + k] * in_stride[k];
+      in_offset_[j] += indices_ptr[j * idx_stride + k] * in_stride.at(k);
     }
   }
 
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/gather_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/gather_fp32.cc
index caea551a702..2e23dddd833 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/gather_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/gather_fp32.cc
@@ -55,14 +55,14 @@ int GatherCPUKernel::DoGather(int task_id) {
   int indices_element_size = indices_tensor->ElementsNum();
   auto axis = (reinterpret_cast<GatherParameter *>(op_parameter_))->axis_;
 
-  const int limit = in_shape[axis];
+  const int limit = in_shape.at(axis);
 
   int outer_size = 1, inner_size = 1;
   for (int i = 0; i < axis; ++i) {
-    outer_size *= in_shape[i];
+    outer_size *= in_shape.at(i);
   }
   for (int i = axis + 1; i < in_rank; ++i) {
-    inner_size *= in_shape[i];
+    inner_size *= in_shape.at(i);
   }
   int stride = UP_DIV(outer_size, op_parameter_->thread_num_);
   int count = MSMIN(stride, outer_size - stride * task_id);
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/group_convolution_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/group_convolution_fp32.cc
index 043596bde98..c4ff456a100 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/group_convolution_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/group_convolution_fp32.cc
@@ -28,7 +28,7 @@ using mindspore::schema::PrimitiveType_Conv2D;
 namespace mindspore::kernel {
 int GroupConvolutionCPUKernel::Init() {
   for (int i = 0; i < group_num_; ++i) {
-    auto ret = group_convs_[i]->Init();
+    auto ret = group_convs_.at(i)->Init();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "Sub kernel init failed.";
       return ret;
@@ -40,7 +40,7 @@ int GroupConvolutionCPUKernel::Init() {
 
 int GroupConvolutionCPUKernel::ReSize() {
   for (int i = 0; i < group_num_; ++i) {
-    auto ret = group_convs_[i]->ReSize();
+    auto ret = group_convs_.at(i)->ReSize();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "Sub kernel resize failed.";
       return RET_ERROR;
@@ -94,7 +94,7 @@ int GroupConvolutionCPUKernel::PreProcess() {
       int in_w = conv_param_->input_w_;
       int in_c = conv_param_->input_channel_;
       in_shape = {in_batch, in_h, in_w, in_c};
-      auto sub_kernel_in_tensor = group_convs_[i]->in_tensors().front();
+      auto sub_kernel_in_tensor = group_convs_.at(i)->in_tensors().front();
       sub_kernel_in_tensor->set_shape(in_shape);
       ret = sub_kernel_in_tensor->MallocData();
       if (ret != RET_OK) {
@@ -108,7 +108,7 @@ int GroupConvolutionCPUKernel::PreProcess() {
       int out_w = conv_param_->output_w_;
       int out_c = conv_param_->output_channel_;
       out_shape = {out_batch, out_h, out_w, out_c};
-      auto sub_kernel_out_tensors = group_convs_[i]->out_tensors();
+      auto sub_kernel_out_tensors = group_convs_.at(i)->out_tensors();
       for (auto tensor : sub_kernel_out_tensors) {
         tensor->set_shape(out_shape);
         ret = tensor->MallocData();
@@ -140,7 +140,7 @@ void GroupConvolutionCPUKernel::SeparateInput(int group_id) {
   int in_plane = in_h * in_w;
   int sub_in_channel = conv_param_->input_channel_;
   int ori_in_channel = sub_in_channel * group_num_;
-  auto sub_in_data = reinterpret_cast<float *>(group_convs_[group_id]->in_tensors().front()->data_c());
+  auto sub_in_data = reinterpret_cast<float *>(group_convs_.at(group_id)->in_tensors().front()->data_c());
   float *src_ptr = ori_in_data_ + group_id * sub_in_channel;
   float *dst_ptr = sub_in_data;
   for (int i = 0; i < in_plane; ++i) {
@@ -156,7 +156,7 @@ void GroupConvolutionCPUKernel::PostConcat(int group_id) {
   int out_plane = out_h * out_w;
   int sub_out_channel = conv_param_->output_channel_;
   int ori_out_channel = sub_out_channel * group_num_;
-  auto sub_out_data = reinterpret_cast<float *>(group_convs_[group_id]->out_tensors().front()->data_c());
+  auto sub_out_data = reinterpret_cast<float *>(group_convs_.at(group_id)->out_tensors().front()->data_c());
   float *src_ptr = sub_out_data;
   float *dst_ptr = ori_out_data_ + group_id * sub_out_channel;
   for (int i = 0; i < out_plane; ++i) {
@@ -173,7 +173,7 @@ int GroupConvolutionCPUKernel::Run() {
     // first, separate group conv input into several parts. This step must be in runtime stage.
     SeparateInput(i);
     // sun kernels run
-    auto ret = group_convs_[i]->Run();
+    auto ret = group_convs_.at(i)->Run();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "sub kernel " << i << " execute failed.";
       return ret;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/instance_norm_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/instance_norm_fp32.cc
index 60d48f8b302..a98142e0e14 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/instance_norm_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/instance_norm_fp32.cc
@@ -36,12 +36,12 @@ int InstanceNormCPUKernel::Init() {
 int InstanceNormCPUKernel::ReSize() {
   auto input_shapes = in_tensors_.front()->shape();
   auto n_dim = input_shapes.size();
-  outer_size_ = input_shapes[0] * input_shapes[n_dim - 1];
+  outer_size_ = input_shapes.at(0) * input_shapes.at(n_dim - 1);
   inner_size_ = 1;
   for (size_t i = 0; i < n_dim - 1; ++i) {
-    inner_size_ *= input_shapes[i];
+    inner_size_ *= input_shapes.at(i);
   }
-  param_->channel_ = input_shapes[n_dim - 1];
+  param_->channel_ = input_shapes.at(n_dim - 1);
   return RET_OK;
 }
 
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/layer_norm_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/layer_norm_fp32.cc
index 9492c7951a9..2ab1ddd326c 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/layer_norm_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/layer_norm_fp32.cc
@@ -39,9 +39,9 @@ int LayerNormCPUKernel::ReSize() {
   inner_size_ = 1;
   for (size_t i = 0; i < shape.size(); ++i) {
     if (i + param_->normalized_dims_ < shape.size()) {
-      outer_size_ *= shape[i];
+      outer_size_ *= shape.at(i);
     } else {
-      inner_size_ *= shape[i];
+      inner_size_ *= shape.at(i);
     }
   }
   return RET_OK;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/local_response_norm_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/local_response_norm_fp32.cc
index 12e20499a1e..94d5dced9bf 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/local_response_norm_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/local_response_norm_fp32.cc
@@ -42,10 +42,10 @@ int LocalResponseNormCPUKernel::DoLocalResponseNorm(int task_id) {
   auto in_shape = input_tensor->shape();
   MS_ASSERT(in_shape.size() == 4);
 
-  int batch = in_shape[0];
-  int height = in_shape[1];
-  int width = in_shape[2];
-  int channel = in_shape[3];
+  int batch = in_shape.at(0);
+  int height = in_shape.at(1);
+  int width = in_shape.at(2);
+  int channel = in_shape.at(3);
 
   int outer_size = batch * width * height;
   int stride = UP_DIV(outer_size, thread_count_);
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/lstm_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/lstm_fp32.cc
index cfd72a2991f..39d13719845 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/lstm_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/lstm_fp32.cc
@@ -50,14 +50,14 @@ int LstmCPUKernel::InitParam() {
   auto input = in_tensors_.front();
   MS_ASSERT(input != nullptr);
   std::vector<int> in_shape = input->shape();
-  lstm_parm_->seq_len_ = in_shape[0];
-  lstm_parm_->batch_ = in_shape[1];
-  lstm_parm_->input_size_ = in_shape[2];
+  lstm_parm_->seq_len_ = in_shape.at(0);
+  lstm_parm_->batch_ = in_shape.at(1);
+  lstm_parm_->input_size_ = in_shape.at(2);
 
-  auto weight_i = in_tensors_[1];
+  auto weight_i = in_tensors_.at(1);
   MS_ASSERT(weight_i != nullptr);
   std::vector<int> w_shape = weight_i->shape();
-  lstm_parm_->hidden_size_ = w_shape[1] / 4;
+  lstm_parm_->hidden_size_ = w_shape.at(1) / 4;
 
   lstm_parm_->input_step_ = lstm_parm_->batch_ * lstm_parm_->input_size_;
   lstm_parm_->output_step_ = lstm_parm_->bidirectional_ ? 2 * lstm_parm_->batch_ * lstm_parm_->hidden_size_
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/matmul_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/matmul_fp32.cc
index e38a0b3eb00..6796d2133b2 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/matmul_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/matmul_fp32.cc
@@ -58,8 +58,9 @@ void MatmulCPUKernel::FreeTmpBuffer() {
 }
 
 int MatmulCPUKernel::MallocMatrixABuffer() {
-  auto a_shape = in_tensors_[0]->shape();
+  auto a_shape = in_tensors_.at(0)->shape();
   int batch = 1;
+  MS_ASSERT(a_shape.size() >= 2);
   for (size_t i = 0; i < a_shape.size() - 2; ++i) {
     batch *= a_shape[i];
   }
@@ -102,11 +103,12 @@ int MatmulCPUKernel::MallocMatrixABuffer() {
 }
 
 int MatmulCPUKernel::MallocMatrixBBuffer() {
-  auto b_shape = in_tensors_[1]->shape();
+  auto b_shape = in_tensors_.at(1)->shape();
   if (b_shape.empty()) {
     return RET_OK;
   }
   int batch = 1;
+  MS_ASSERT(b_shape.size() >= 2);
   for (size_t i = 0; i < b_shape.size() - 2; ++i) {
     batch *= b_shape[i];
   }
@@ -133,11 +135,11 @@ int MatmulCPUKernel::MallocMatrixBBuffer() {
 }
 
 int MatmulCPUKernel::InitBias() {
-  auto b_shape = in_tensors_[1]->shape();
-  auto c_shape = out_tensors_[0]->shape();
+  auto b_shape = in_tensors_.at(1)->shape();
+  auto c_shape = out_tensors_.at(0)->shape();
   params_->col_ = params_->b_const_
-                    ? (params_->b_transpose_ ? b_shape[b_shape.size() - 2] : b_shape[b_shape.size() - 1])
-                    : (c_shape[c_shape.size() - 1]);
+                    ? (params_->b_transpose_ ? b_shape.at(b_shape.size() - 2) : b_shape.at(b_shape.size() - 1))
+                    : (c_shape.at(c_shape.size() - 1));
   params_->col_8_ = UP_ROUND(params_->col_, 8);
   auto col_tmp = is_vector_a_ ? params_->col_ : params_->col_8_;
   if (bias_ptr_ == nullptr) {
@@ -221,15 +223,15 @@ void MatmulCPUKernel::InitMatrixB(const float *src_ptr, float *dst_ptr) {
 }
 
 int MatmulCPUKernel::Init() {
-  params_->a_const_ = (in_tensors_[0]->data_c() != nullptr);
-  params_->b_const_ = (in_tensors_[1]->data_c() != nullptr);
+  params_->a_const_ = (in_tensors_.at(0)->data_c() != nullptr);
+  params_->b_const_ = (in_tensors_.at(1)->data_c() != nullptr);
   if (params_->a_const_) {
     auto ret = MallocMatrixABuffer();
     if (ret != RET_OK) {
       MS_LOG(ERROR) << "Matmul fp32 malloc matrix Ａ buffer failed";
       return RET_ERROR;
     }
-    InitMatrixA(reinterpret_cast<float *>(in_tensors_[0]->data_c()), a_pack_ptr_);
+    InitMatrixA(reinterpret_cast<float *>(in_tensors_.at(0)->data_c()), a_pack_ptr_);
     a_ptr_ = a_pack_ptr_;
   }
   if (params_->b_const_) {
@@ -238,7 +240,7 @@ int MatmulCPUKernel::Init() {
       MS_LOG(ERROR) << "Matmul fp32 malloc matrix B buffer failed";
       return RET_ERROR;
     }
-    InitMatrixB(reinterpret_cast<float *>(in_tensors_[1]->data_c()), b_pack_ptr_);
+    InitMatrixB(reinterpret_cast<float *>(in_tensors_.at(1)->data_c()), b_pack_ptr_);
     b_ptr_ = b_pack_ptr_;
     // init bias
     ret = InitBias();
@@ -281,9 +283,9 @@ int MatmulFloatRun(void *cdata, int task_id) {
 }
 
 int MatmulCPUKernel::Run() {
-  auto a_src = reinterpret_cast<float *>(in_tensors_[0]->data_c());
-  auto b_src = reinterpret_cast<float *>(in_tensors_[1]->data_c());
-  auto c_src = reinterpret_cast<float *>(out_tensors_[0]->data_c());
+  auto a_src = reinterpret_cast<float *>(in_tensors_.at(0)->data_c());
+  auto b_src = reinterpret_cast<float *>(in_tensors_.at(1)->data_c());
+  auto c_src = reinterpret_cast<float *>(out_tensors_.at(0)->data_c());
 
   if (!params_->a_const_ || IsTrain()) {
     if (a_pack_ptr_ != nullptr) {
@@ -356,8 +358,8 @@ int MatmulCPUKernel::Run() {
 
 int MatmulCPUKernel::Eval() {
   // Copy weights after training
-  auto a_src = reinterpret_cast<float *>(in_tensors_[0]->data_c());
-  auto b_src = reinterpret_cast<float *>(in_tensors_[1]->data_c());
+  auto a_src = reinterpret_cast<float *>(in_tensors_.at(0)->data_c());
+  auto b_src = reinterpret_cast<float *>(in_tensors_.at(1)->data_c());
   LiteKernel::Eval();
   if (params_->a_const_) {
     if (a_pack_ptr_ == nullptr) {
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/nchw2nhwc_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/nchw2nhwc_fp32.cc
index 2b8b3e33d6e..6c1acf79827 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/nchw2nhwc_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/nchw2nhwc_fp32.cc
@@ -28,8 +28,8 @@ int Nchw2NhwcCPUKernel::Init() { return RET_OK; }
 int Nchw2NhwcCPUKernel::ReSize() { return RET_OK; }
 
 int Nchw2NhwcCPUKernel::Run() {
-  auto input = in_tensors_[0];
-  auto output = out_tensors_[0];
+  auto input = in_tensors_.at(0);
+  auto output = out_tensors_.at(0);
 
   if (input->shape().size() == 4) {
     if (input->data_type() == kNumberTypeFloat32) {
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/nhwc2nchw_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/nhwc2nchw_fp32.cc
index 49112ed8eda..0bcc47fb96b 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/nhwc2nchw_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/nhwc2nchw_fp32.cc
@@ -28,8 +28,8 @@ int Nhwc2NchwCPUKernel::Init() { return RET_OK; }
 int Nhwc2NchwCPUKernel::ReSize() { return RET_OK; }
 
 int Nhwc2NchwCPUKernel::Run() {
-  auto input = in_tensors_[0];
-  auto output = out_tensors_[0];
+  auto input = in_tensors_.at(0);
+  auto output = out_tensors_.at(0);
 
   if (input->shape().size() == 4) {
     if (input->data_type() == kNumberTypeFloat32) {
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/non_max_suppression_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/non_max_suppression_fp32.cc
index 738b3cf46e3..c8fc2abd412 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/non_max_suppression_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/non_max_suppression_fp32.cc
@@ -122,13 +122,13 @@ int NonMaxSuppressionCPUKernel::Run() {
     return RET_ERROR;
   }
   constexpr size_t kBatchIndex = 0;
-  if (score_dims[kBatchIndex] != box_dims[kBatchIndex]) {
+  if (score_dims.at(kBatchIndex) != box_dims.at(kBatchIndex)) {
     MS_LOG(ERROR) << "Boxes tensor batch num should be equal to scores tensor's batch num.";
     return RET_ERROR;
   }
   constexpr size_t kScoreDimsBoxNumIndex = 2;
   constexpr size_t kBoxDimsBoxNumIndex = 1;
-  if (score_dims[kScoreDimsBoxNumIndex] != box_dims[kBoxDimsBoxNumIndex]) {
+  if (score_dims.at(kScoreDimsBoxNumIndex) != box_dims.at(kBoxDimsBoxNumIndex)) {
     MS_LOG(ERROR) << "Boxes tensor spatial dimension should be equal to scores tensor's spatial dimension.";
     return RET_ERROR;
   }
@@ -138,10 +138,10 @@ int NonMaxSuppressionCPUKernel::Run() {
     return RET_ERROR;
   }
 
-  int batch_num = score_dims[kBatchIndex];
+  int batch_num = score_dims.at(kBatchIndex);
   constexpr size_t kClassIndex = 1;
-  int class_num = score_dims[kClassIndex];
-  int box_num = score_dims[kScoreDimsBoxNumIndex];
+  int class_num = score_dims.at(kClassIndex);
+  int box_num = score_dims.at(kScoreDimsBoxNumIndex);
   float *scores_data = reinterpret_cast<float *>(score_tensor->data_c());
   if (scores_data == nullptr) {
     MS_LOG(ERROR) << "score tensor data nullptr";
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/power_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/power_fp32.cc
index 3920b0e9dcc..ad65a8accb0 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/power_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/power_fp32.cc
@@ -50,11 +50,11 @@ int PowerCPUKernel::Run() {
 }
 
 int PowerCPUKernel::RunImpl(int task_id) {
-  auto x_addr = reinterpret_cast<float *>(in_tensors_[0]->MutableData());
+  auto x_addr = reinterpret_cast<float *>(in_tensors_.at(0)->MutableData());
   MS_ASSERT(x_addr);
-  auto output_addr = reinterpret_cast<float *>(out_tensors_[0]->MutableData());
+  auto output_addr = reinterpret_cast<float *>(out_tensors_.at(0)->MutableData());
   MS_ASSERT(output_addr);
-  auto size = in_tensors_[0]->ElementsNum();
+  auto size = in_tensors_.at(0)->ElementsNum();
   int stride = UP_DIV(size, thread_count_);
   int len = MSMIN(stride, size - stride * task_id);
   float *exp_addr = nullptr;
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/prelu_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/prelu_fp32.cc
index 7f487cf2f9f..545fede2059 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/prelu_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/prelu_fp32.cc
@@ -52,13 +52,13 @@ int PReluCPUKernel::DoExcute(int task_id) {
 
 int PReluCPUKernel::ProcessInput() {
   // input tensor
-  auto input_tensor = in_tensors_[0];
+  auto input_tensor = in_tensors_.at(0);
   auto in_shape = input_tensor->shape();
   auto n_dim = in_shape.size();
   auto channel_num = in_shape.at(n_dim - 1);
   int input_plane = 1;
   for (size_t i = 0; i < n_dim - 1; ++i) {
-    input_plane *= in_shape[i];
+    input_plane *= in_shape.at(i);
   }
   int tile_block = UP_DIV(input_plane, TILE_NUM);
   prelu_param_->input_num_ = input_tensor->ElementsNum();
@@ -76,7 +76,7 @@ int PReluCPUKernel::ProcessInput() {
 
 int PReluCPUKernel::ProcessShareChannelInput() {
   // input tensor
-  auto input_tensor = in_tensors_[0];
+  auto input_tensor = in_tensors_.at(0);
   prelu_param_->input_num_ = input_tensor->ElementsNum();
 #ifdef ENABLE_ARM64
   prelu_param_->tile_block_ = UP_DIV(prelu_param_->input_num_, 64);
diff --git a/mindspore/lite/src/runtime/kernel/arm/fp32/rank_fp32.cc b/mindspore/lite/src/runtime/kernel/arm/fp32/rank_fp32.cc
index 2c0b87d48bf..39dba85a287 100644
--- a/mindspore/lite/src/runtime/kernel/arm/fp32/rank_fp32.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/fp32/rank_fp32.cc
@@ -34,7 +34,7 @@ int RankCPUKernel::ReSize() { return RET_OK; }
 int RankCPUKernel::Run() {
   auto output_ptr = reinterpret_cast<float *>(out_tensors_.at(0)->MutableData());
   MS_ASSERT(output_ptr);
-  auto in_shape = in_tensors_[0]->shape();
+  auto in_shape = in_tensors_.at(0)->shape();
   auto rank = in_shape.size();
   Rank(output_ptr, rank);
   return RET_OK;
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/fullconnection_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/fullconnection_int8.cc
index 57f3b0f1fe6..5949d894f86 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/fullconnection_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/fullconnection_int8.cc
@@ -74,7 +74,7 @@ void FullconnectionInt8CPUKernel::FreeTmpBuffer() {
 }
 
 int FullconnectionInt8CPUKernel::MallocQuantParam() {
-  auto weight_tensor = in_tensors_[1];
+  auto weight_tensor = in_tensors_.at(1);
   auto weight_quant_params = weight_tensor->quant_params();
   int col = weight_tensor->shape().front();
   filter_per_channel_ = (weight_quant_params.size() > 1);
@@ -111,15 +111,15 @@ int FullconnectionInt8CPUKernel::Init() {
     return ret;
   }
 
-  auto in_quant_params = in_tensors_[0]->quant_params();
+  auto in_quant_params = in_tensors_.at(0)->quant_params();
   quant_.input_.zp_ = in_quant_params.front().zeroPoint;
   quant_.input_.scale_ = in_quant_params.front().scale;
 
-  auto out_quant_params = out_tensors_[0]->quant_params();
+  auto out_quant_params = out_tensors_.at(0)->quant_params();
   quant_.output_.zp_ = out_quant_params.front().zeroPoint;
   quant_.output_.scale_ = out_quant_params.front().scale;
 
-  auto weight_tensor = in_tensors_[1];
+  auto weight_tensor = in_tensors_.at(1);
   fc_param_->b_const_ = (weight_tensor->data_c() != nullptr);
   int weight_quant_num = filter_per_channel_ ? weight_tensor->shape().front() : 1;
   auto weight_quant_params = weight_tensor->quant_params();
@@ -148,12 +148,12 @@ int FullconnectionInt8CPUKernel::Init() {
 
 void FullconnectionInt8CPUKernel::InitParam() {
   int row = 1;
-  for (size_t i = 0; i < out_tensors_[0]->shape().size() - 1; ++i) {
-    row *= (out_tensors_[0]->shape())[i];
+  for (size_t i = 0; i < out_tensors_.at(0)->shape().size() - 1; ++i) {
+    row *= (out_tensors_.at(0)->shape()).at(i);
   }
   fc_param_->row_ = row;
-  fc_param_->col_ = out_tensors_[0]->shape().back();
-  fc_param_->deep_ = (in_tensors_[1]->shape())[1];
+  fc_param_->col_ = out_tensors_.at(0)->shape().back();
+  fc_param_->deep_ = (in_tensors_.at(1)->shape()).at(1);
 
   fc_param_->row_4_ = UP_ROUND(fc_param_->row_, C4NUM);
   fc_param_->row_8_ = UP_ROUND(fc_param_->row_, C8NUM);
@@ -207,13 +207,13 @@ int FullconnectionInt8CPUKernel::ReSize() {
       FreeTmpBuffer();
       return RET_MEMORY_FAILED;
     }
-    memcpy(bias_ptr_, in_tensors_[2]->data_c(), fc_param_->col_ * sizeof(int));
+    memcpy(bias_ptr_, in_tensors_.at(2)->data_c(), fc_param_->col_ * sizeof(int));
   } else {
     bias_ptr_ = nullptr;
   }
 
   if (fc_param_->b_const_) {
-    auto weight_data = reinterpret_cast<int8_t *>(in_tensors_[1]->data_c());
+    auto weight_data = reinterpret_cast<int8_t *>(in_tensors_.at(1)->data_c());
     RowMajor2Row16x4MajorInt8(weight_data, pack_b_ptr_, fc_param_->col_, fc_param_->deep_);
     CalcWeightBiasSums(weight_data, fc_param_->deep_, fc_param_->col_, quant_.input_.zp_, quant_.filter_zp_, bias_ptr_,
                        weight_bias_sums_, ColMajor, filter_per_channel_);
@@ -254,20 +254,20 @@ int FcInt8Run(void *cdata, int task_id) {
 }
 
 int FullconnectionInt8CPUKernel::Run() {
-  auto input_ptr = reinterpret_cast<int8_t *>(in_tensors_[0]->data_c());
+  auto input_ptr = reinterpret_cast<int8_t *>(in_tensors_.at(0)->data_c());
   RowMajor2Row16x4MajorInt8(input_ptr, pack_a_ptr_, fc_param_->row_, fc_param_->deep_);
 
   int32_t tmp_weight_zp = filter_per_channel_ ? 1 : quant_.filter_zp_[0];
   CalcInputSums(input_ptr, fc_param_->row_, fc_param_->deep_, tmp_weight_zp, input_sums_, RowMajor);
 
   if (!fc_param_->b_const_) {
-    auto weight_data = reinterpret_cast<int8_t *>(in_tensors_[1]->data_c());
+    auto weight_data = reinterpret_cast<int8_t *>(in_tensors_.at(1)->data_c());
     RowMajor2Row16x4MajorInt8(weight_data, pack_b_ptr_, fc_param_->col_, fc_param_->deep_);
     CalcWeightBiasSums(weight_data, fc_param_->deep_, fc_param_->col_, quant_.input_.zp_, quant_.filter_zp_, bias_ptr_,
                        weight_bias_sums_, ColMajor, filter_per_channel_);
   }
 
-  c_ptr_ = reinterpret_cast<int8_t *>(out_tensors_[0]->data_c());
+  c_ptr_ = reinterpret_cast<int8_t *>(out_tensors_.at(0)->data_c());
   auto ret = ParallelLaunch(this->context_->thread_pool_, FcInt8Run, this, thread_count_);
   if (ret != RET_OK) {
     MS_LOG(ERROR) << "ParallelLaunch failed";
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/gatherNd_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/gatherNd_int8.cc
index e1224c6c2a7..f898886148b 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/gatherNd_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/gatherNd_int8.cc
@@ -77,11 +77,11 @@ int GatherNdInt8CPUKernel::ReSize() {
 
   auto in_shape = in_tensors_.front()->shape();
   int in_rank = in_shape.size();
-  int idx_lastshape = indices_shape[indices_rank - 1];
+  int idx_lastshape = indices_shape.at(indices_rank - 1);
   auto indices_ptr = reinterpret_cast<int8_t *>(indices_tensor->MutableData());
   area_ = 1;
   for (int i = idx_lastshape; i < in_rank; ++i) {
-    area_ *= in_shape[i];
+    area_ *= in_shape.at(i);
   }
   std::vector<int> in_stride(in_rank);
   in_stride[in_rank - 1] = 1;
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/gather_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/gather_int8.cc
index 182b15a1a20..4bee9ced53a 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/gather_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/gather_int8.cc
@@ -61,7 +61,7 @@ int GatherInt8CPUKernel::DoGather(int task_id) {
   int in_rank = in_shape.size();
   int indices_element_size = indices_tensor->ElementsNum();
 
-  const int limit = in_shape[axis_];
+  const int limit = in_shape.at(axis_);
   for (int i = 0; i < indices_element_size; ++i) {
     if (indices_ptr[i] >= limit) {
       MS_LOG(ERROR) << " indice data: " << indices_ptr[i] << " is not in [ 0, " << limit - 1 << " ]";
@@ -71,12 +71,12 @@ int GatherInt8CPUKernel::DoGather(int task_id) {
 
   int outer_size = 1;
   for (int i = 0; i < axis_; ++i) {
-    outer_size *= in_shape[i];
+    outer_size *= in_shape.at(i);
   }
 
   int inner_size = 1;
   for (int i = axis_ + 1; i < in_rank; ++i) {
-    inner_size *= in_shape[i];
+    inner_size *= in_shape.at(i);
   }
 
   int stride = UP_DIV(outer_size, thread_count_);
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/layer_norm_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/layer_norm_int8.cc
index 4e996b3617d..19c5b611c5a 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/layer_norm_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/layer_norm_int8.cc
@@ -89,9 +89,9 @@ int LayerNormInt8CPUKernel::ReSize() {
   inner_size_ = 1;
   for (size_t i = 0; i < shape.size(); ++i) {
     if (i + param_->normalized_dims_ < shape.size()) {
-      outer_size_ *= shape[i];
+      outer_size_ *= shape.at(i);
     } else {
-      inner_size_ *= shape[i];
+      inner_size_ *= shape.at(i);
     }
   }
 
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/leaky_relu_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/leaky_relu_int8.cc
index 4723c96d87d..4dfb5eae694 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/leaky_relu_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/leaky_relu_int8.cc
@@ -85,7 +85,7 @@ int LeakyReluInt8CPUKernel::ReSize() {
   auto *out_tensor = out_tensors_.at(kOutputIndex);
   auto input_dim = input_tensor->shape().size();
   quant_prelu_parm_.input_dim_ = input_dim;
-  quant_prelu_parm_.element_num = in_tensors_[0]->Size();
+  quant_prelu_parm_.element_num = in_tensors_.at(0)->Size();
   auto input_shape = input_tensor->shape();
   if (quant_prelu_parm_.in_shape_ != nullptr) {
     free(quant_prelu_parm_.in_shape_);
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/matmul_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/matmul_int8.cc
index 649858958a3..3ea136c7feb 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/matmul_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/matmul_int8.cc
@@ -39,12 +39,14 @@ int MatmulInt8CPUKernel::Init() {
 int MatmulInt8CPUKernel::ReSize() {
   FreeTmpBuffer();
   int batch = 1;
-  auto x_shape = in_tensors_[0]->shape();
-  auto o_shape = out_tensors_[0]->shape();
+  auto x_shape = in_tensors_.at(0)->shape();
+  auto o_shape = out_tensors_.at(0)->shape();
+  MS_ASSERT(x_shape.size() >= 2);
   for (size_t i = 0; i < x_shape.size() - 2; ++i) {
     batch *= x_shape[i];
   }
   params_->batch = batch;
+  MS_ASSERT(o_shape.size() >= 2);
   params_->row_ = o_shape[o_shape.size() - 2];
   params_->col_ = o_shape[o_shape.size() - 1];
   params_->deep_ = params_->a_transpose_ ? x_shape[x_shape.size() - 2] : x_shape[x_shape.size() - 1];
@@ -77,25 +79,25 @@ int MatmulInt8CPUKernel::ReSize() {
   thread_count_ = MSMIN(thread_count_, UP_DIV(params_->col_4_, 4));
   thread_stride_ = UP_DIV(UP_DIV(params_->col_4_, 4), thread_count_);
 
-  auto input_tensor = in_tensors_[0];
+  auto input_tensor = in_tensors_.at(0);
   auto params = input_tensor->quant_params();
   MS_ASSERT(params.size() == 1);
   quant_params_.input.zp_ = params.front().zeroPoint;
   quant_params_.input.scale_ = params.front().scale;
-  auto weight_tensor = in_tensors_[1];
+  auto weight_tensor = in_tensors_.at(1);
   params = weight_tensor->quant_params();
   MS_ASSERT(params.size() == 1);
   quant_params_.weight.zp_ = params.front().zeroPoint;
   quant_params_.weight.scale_ = params.front().scale;
-  auto output_tensor = out_tensors_[0];
+  auto output_tensor = out_tensors_.at(0);
   params = output_tensor->quant_params();
   MS_ASSERT(params.size() == 1);
   quant_params_.output.zp_ = params.front().zeroPoint;
   quant_params_.output.scale_ = params.front().scale;
 
-  params_->b_const_ = (in_tensors_[1]->data_c() != nullptr);
+  params_->b_const_ = (in_tensors_.at(1)->data_c() != nullptr);
   if (params_->b_const_) {
-    auto b_ptr = reinterpret_cast<int8_t *>(in_tensors_[1]->data_c());
+    auto b_ptr = reinterpret_cast<int8_t *>(in_tensors_.at(1)->data_c());
     for (int i = 0; i < params_->batch; ++i) {
       auto cur_b = b_ptr + i * params_->deep_ * params_->col_;
       auto cur_b_pack = b_c16x4_batch_ + i * params_->col_4_ * params_->deep_16_;
@@ -152,14 +154,14 @@ int MatmulInt8Run(void *cdata, int task_id) {
 }
 
 int MatmulInt8CPUKernel::Run() {
-  auto a_ptr = reinterpret_cast<int8_t *>(in_tensors_[0]->data_c());
-  auto c_ptr = reinterpret_cast<int8_t *>(out_tensors_[0]->data_c());
+  auto a_ptr = reinterpret_cast<int8_t *>(in_tensors_.at(0)->data_c());
+  auto c_ptr = reinterpret_cast<int8_t *>(out_tensors_.at(0)->data_c());
   auto a_stride = params_->row_ * params_->deep_;
   auto b_stride = params_->deep_ * params_->col_;
   auto c_stride = params_->row_ * params_->col_;
 
   if (!params_->b_const_) {
-    auto b_ptr = reinterpret_cast<int8_t *>(in_tensors_[1]->data_c());
+    auto b_ptr = reinterpret_cast<int8_t *>(in_tensors_.at(1)->data_c());
     for (int i = 0; i < params_->batch; ++i) {
       auto cur_b = b_ptr + i * b_stride;
       auto cur_b_pack = b_c16x4_batch_ + i * params_->col_4_ * params_->deep_16_;
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/pad_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/pad_int8.cc
index fa9ae52eb02..eb779cad2c2 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/pad_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/pad_int8.cc
@@ -87,8 +87,8 @@ int PadInt8CPUKernel::SetQuantParam() {
 }
 
 int PadInt8CPUKernel::InitPadParam() {
-  auto in_dims = in_tensors_[0]->shape();
-  auto out_dims = out_tensors_[0]->shape();
+  auto in_dims = in_tensors_.at(0)->shape();
+  auto out_dims = out_tensors_.at(0)->shape();
   int ndims = in_dims.size();
 
   int in[] = {1, 1, 1, 1};
@@ -265,8 +265,8 @@ int PadInt8CPUKernel::CopyPaddingFromInput() {
 }
 
 int PadInt8CPUKernel::Run() {
-  in_data_ = reinterpret_cast<int8_t *>(in_tensors_[0]->MutableData());
-  out_data_ = reinterpret_cast<int8_t *>(out_tensors_[0]->MutableData());
+  in_data_ = reinterpret_cast<int8_t *>(in_tensors_.at(0)->MutableData());
+  out_data_ = reinterpret_cast<int8_t *>(out_tensors_.at(0)->MutableData());
 
   int error_code;
   if (pad_param_->pad_mode_ == static_cast<int>(schema::PaddingMode_CONSTANT)) {
diff --git a/mindspore/lite/src/runtime/kernel/arm/int8/power_int8.cc b/mindspore/lite/src/runtime/kernel/arm/int8/power_int8.cc
index 56ecf17493a..59a9fe33ff6 100644
--- a/mindspore/lite/src/runtime/kernel/arm/int8/power_int8.cc
+++ b/mindspore/lite/src/runtime/kernel/arm/int8/power_int8.cc
@@ -66,7 +66,7 @@ int PowerInt8CPUKernel::DoPower(int task_id) {
   int8_t *output_data = reinterpret_cast<int8_t *>(out_tensors_[0]->MutableData());
   MS_ASSERT(output_data);
 
-  auto size = in_tensors_[0]->ElementsNum();
+  auto size = in_tensors_.at(0)->ElementsNum();
   int stride = UP_DIV(size, op_parameter_->thread_num_);
   int count = MSMIN(stride, size - stride * task_id);
   int8_t *exp_ptr = nullptr;